Mike
commited on
Commit
•
0509158
1
Parent(s):
d8a5533
add files to spaces.
Browse files- app.py +57 -0
- requirements.txt +3 -0
app.py
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import pipeline
|
3 |
+
|
4 |
+
token_skill_classifier = pipeline(model="jjzha/escoxlmr_skill_extraction", aggregation_strategy="first")
|
5 |
+
token_knowledge_classifier = pipeline(model="jjzha/escoxlmr_knowledge_extraction", aggregation_strategy="first")
|
6 |
+
|
7 |
+
|
8 |
+
examples = [
|
9 |
+
"Knowing Python is a plus",
|
10 |
+
"Recommend changes, develop and implement processes to ensure compliance with IFRS standards"
|
11 |
+
]
|
12 |
+
|
13 |
+
|
14 |
+
def aggregate_span(results):
|
15 |
+
new_results = []
|
16 |
+
current_result = results[0]
|
17 |
+
|
18 |
+
for result in results[1:]:
|
19 |
+
if result["start"] == current_result["end"] + 1:
|
20 |
+
current_result["word"] += " " + result["word"]
|
21 |
+
current_result["end"] = result["end"]
|
22 |
+
else:
|
23 |
+
new_results.append(current_result)
|
24 |
+
current_result = result
|
25 |
+
|
26 |
+
new_results.append(current_result)
|
27 |
+
|
28 |
+
return new_results
|
29 |
+
|
30 |
+
|
31 |
+
def ner(text):
|
32 |
+
output_skills = token_skill_classifier(text)
|
33 |
+
for result in output_skills:
|
34 |
+
if result.get("entity_group"):
|
35 |
+
result["entity"] = "Skill"
|
36 |
+
del result["entity_group"]
|
37 |
+
|
38 |
+
output_knowledge = token_knowledge_classifier(text)
|
39 |
+
for result in output_knowledge:
|
40 |
+
if result.get("entity_group"):
|
41 |
+
result["entity"] = "Knowledge"
|
42 |
+
del result["entity_group"]
|
43 |
+
|
44 |
+
if len(output_skills) > 0:
|
45 |
+
output_skills = aggregate_span(output_skills)
|
46 |
+
if len(output_knowledge) > 0:
|
47 |
+
output_knowledge = aggregate_span(output_knowledge)
|
48 |
+
|
49 |
+
return {"text": text, "entities": output_skills}, {"text": text, "entities": output_knowledge}
|
50 |
+
|
51 |
+
|
52 |
+
demo = gr.Interface(fn=ner,
|
53 |
+
inputs=gr.Textbox(placeholder="Enter sentence here..."),
|
54 |
+
outputs=["highlight", "highlight"],
|
55 |
+
examples=examples)
|
56 |
+
|
57 |
+
demo.launch()
|
requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
transformers
|
2 |
+
gradio
|
3 |
+
torch
|